In low signal-to-noise ratio (SNR) acoustic scenarios, it remains fairly challenging to extract the target speech from its noisy mixture. In this paper, we propose a collaborative-style framework, namely, filtering and refining network (FRNet) for single-channel speech enhancement, recovering the complex spectrum of the target speech from coarse and fine-grained perspectives. Specifically, we devise a two-branch structure dubbed filtering-refining module (FRM). In the filtering block, the phase impact is ignored, and we only focus on coarse filtering in the magnitude domain. In the refining block, instead of predicting the irregular phase distribution directly, we estimate the complex residual for phase modification and spectrum rehabilitation, which takes the harmonic structure but with rather sparse energy distribution. By cascading FRMs repeatedly, we can reconstruct the target spectrum progressively. Furthermore, we propose a two-stream feature encoder to extract the feature representation of magnitude and phase individually, and the utilization of feature recalibration layers can preserve the prominent information from multiple scales. Extensive experiments are conducted on the WSJ0-SI84, Voicebank+Demand, and DNS-Challenge corpora. Evaluation results show that the proposed system performs favorably against previous advanced systems and achieves overall state-of-the-art performance in PESQ, ESTOI, SDR, and DNSMOS metrics.

Recommendation system has drawn growing attention in the academia and industry because it can solve the problem of information overload. Among a variety of methods, the click-through rate prediction model plays an important role in predicting user’s attention to a specific item. To predict click-through rate, high-dimensional and sparse features are usually adopted, and the accuracy of the prediction result depends on the combination of high-order features to a great extent. Therefore, many methods have been proposed to find the low-dimensional representation from sparse high-dimensional original features, and the meaningful way of feature combination has also been mined to improve the accuracy of the model. However, the click-through rate prediction models generally have two problems. One is that they can’t extract the feature interaction of non-Euclidean features very well. Another one is that it is hard to explain the inward meaning of feature interaction. In this paper, a GCN-int model based on the interaction of Graph Convolutional Network is proposed to solve the above problems. The proposed model simplifies the complex interaction among multiple features, gets a better representation of the interaction between high-order features, and improves the interpretability of feature interaction. The experimental results on the public movie recommendation dataset and our own IPTV movie recommendation dataset show that the proposed GCN-int model gets higher accuracy and efficiency compared with the state-of-the-art models.

Knowledge graph (KG)-based recommendation methods effectively alleviate the data sparsity and cold-start problems in collaborative filtering. Among these methods, neighborhood-based methods are the mainstream methods. However, these methods ignore some meta-information about the items, specifically, the diversity of item information (e.g., texts) and feature interaction between neighboring nodes. In this paper, we propose a Bilinear Knowledge-aware Graph Neural Network Fusing Text Information (BKGNN-TI), which can model both knowledge graph information and text information. In particular, the information in knowledge graph contains not only the existing high-order connectivity but also feature interactions between neighboring nodes at the same level in KG. First, we construct the information propagation layer using the bilinear collector and linear collector. Feature interactions between neighboring nodes and the high-order connectivity are collected in the information propagation layer to generate the item knowledge representations. The bilinear collector emphasizes the importance of second-order feature interaction between neighboring nodes in the KG. Then, texts are also introduced when computing the item representations, which can help further infer user interests. We choose objective program titles and introductions as text information to avoid the influence of subjective factors. BKGNN-TI designs an ALBERT-based sequence encoder to encode texts by the structure of ALBERT+Bi-LSTM+Attention, thus enriching the feature representations of the items. In the experiments, we utilize two language datasets, i.e., the English public dataset Movielens-20M and the Chinese dataset IPTV constructed by ourselves. The results demonstrate that our BKGNN-TI outperforms baselines, indicating that our BKGNN-TI is a generalization for both Chinese and English datasets.

The ability to localize a sound source is very important in our daily life, specifically to analyze auditory scenes in complex acoustic environments. The concept of minimum audible angle (MAA), which is defined as the smallest detectable difference between the incident directions of two sound sources, has been widely used in the research fields of auditory perception to measure localization ability. Measuring MAAs usually involves a reference sound source and either a large number of loudspeakers or a movable sound source in order to reproduce sound sources at a large number of predefined incident directions. However, existing MAA test systems are often cumbersome because they require a large number of loudspeakers or a mechanical rail slide and thus are expensive and inconvenient to use. This study investigates a novel MAA test method using virtual sound source synthesis and avoiding the problems with traditional methods. We compare the perceptual localization acuity of sound sources in two experimental designs: using the virtual presentation and real sound sources. The virtual sound source is reproduced through a pair of loudspeakers weighted by vector-based amplitude panning (VBAP). Results show that the average measured MAA at 0° azimuth is 1.1° and the average measured MAA at 90° azimuth is 3.1° in a virtual acoustic system, meanwhile the average measured MAA at 0° azimuth is about 1.2° and the average measured MAA at 90° azimuth is 3.3° when using the real sound sources. The measurements of the two methods have no significant difference. We conclude that the proposed MAA test system is a suitable alternative to more complicated and expensive setups.